Comparing in- and out-of-sample approaches to variance decomposition-based estimates of network connectedness an application to the Italian banking system

Andrea Ferrario; Massimo Guidolin; Manuela Pedio; Andrea Ferrario; Massimo Guidolin; Manuela Pedio

doi:10.3934/QFE.2018.3.661

Quantitative Finance and Economics

2018, Volume 2, Issue 3: 661-701. doi: 10.3934/QFE.2018.3.661

Previous Article Next Article

Research article Special Issues

Comparing in- and out-of-sample approaches to variance decomposition-based estimates of network connectedness an application to the Italian banking system

1.
Bocconi University, Via Roentgen 1, 20136 Milan, Italy
2.
Baffi-CAREFIN Centre and Department of Finance, Bocconi University, Via Roentgen 1, 20136 Milan, Italy

Received: 16 April 2018 Accepted: 27 June 2018 Published: 17 August 2018
JEL Codes: G21, C32, D85

We use methods that exploit variance decompositions from standard (rolling window) estimates of VAR(p) models to obtain estimates of network connectedness and perform an empirical comparison of the results derived under two alternative approaches: To base the decompositions on in-sample forecast errors vs. out-of-sample forecast errors derived from a separation between estimation and forecast evaluation window. Using the intraday realized variance of bank stock return, we derive novel empirical results on the systemic risk of the Italian banking system, whose network connectedness turns out to be generally high, increasing over time especially during the Great Financial and the European sovereign debt crises. However, whether a few net exporters of systemic risk may be reliably estimated turns out to depend on the methodology adopted when computing rolling window variance decompositions.
- networks,
- connectedness measures,
- vector autoregressions,
- generalized variance decompositions,
- banking system,
- contagion and spillovers
Citation: Andrea Ferrario, Massimo Guidolin, Manuela Pedio. Comparing in- and out-of-sample approaches to variance decomposition-based estimates of network connectedness an application to the Italian banking system[J]. Quantitative Finance and Economics, 2018, 2(3): 661-701. doi: 10.3934/QFE.2018.3.661

Related Papers:

Abstract

We use methods that exploit variance decompositions from standard (rolling window) estimates of VAR(p) models to obtain estimates of network connectedness and perform an empirical comparison of the results derived under two alternative approaches: To base the decompositions on in-sample forecast errors vs. out-of-sample forecast errors derived from a separation between estimation and forecast evaluation window. Using the intraday realized variance of bank stock return, we derive novel empirical results on the systemic risk of the Italian banking system, whose network connectedness turns out to be generally high, increasing over time especially during the Great Financial and the European sovereign debt crises. However, whether a few net exporters of systemic risk may be reliably estimated turns out to depend on the methodology adopted when computing rolling window variance decompositions.

References

[1]	Ahelegbey DF, Billio M, Casarin R (2015) Bayesian Graphical Models for Structural Vector Autoregressive Processes. J Appl Econ 31: 357–386.
[2]	Alter A, Beyer A (2014) The dynamics of spillover effects during the European sovereign debt turmoil. J Banking Finance 42: 134–153. doi: 10.1016/j.jbankfin.2014.01.030
[3]	Benjamini Y, Yekutieli D (2001) The control of the false discovery rate in multiple testing under dependency. Ann Stat 29: 1165–1188. doi: 10.1214/aos/1013699998
[4]	Betz F, Hautsch N, Peltonen T, et al. (2016) Systemic risk spillovers in the European banking and sovereign network. J Financ Stab 25: 206–224.
[5]	Borri N, Caccavaio M, Giorgio GD, et al. (2014) Systemic risk in the Italian banking industry. Econ Notes 43: 21–38. doi: 10.1111/ecno.12015
[6]	Davies P, Time to remove Italian banks from list of global worries, Wall Street Journal, November 9, 2017. Available from: https://www.wsj.com/articles/time-to-remove-italian-banks-from-list-of-global-worries-1510238322.
[7]	Demirer M, Diebold FX, Liu L, et al. (2018) Estimating global bank network connectedness. J Appl Econ 33: 1–15. doi: 10.1002/jae.2598
[8]	Biase PD, D'Apolito E (2012) The determinants of systematic risk in the Italian banking system: A cross-sectional time series analysis. Int J Econ Finance 4: 152–164.
[9]	Diebold FX, Yilmaz K (2009) Measuring financial asset return and volatility spillovers, with application to global equity markets. Econ J 119: 158–171.
[10]	Diebold FX, Yilmaz K (2012) Better to give than to receive: Predictive directional measurement of volatility spillovers. Int J Forecasting 28: 57–66. doi: 10.1016/j.ijforecast.2011.02.006
[11]	Diebold FX, Yilmaz K (2014) On the network topology of variance decompositions: Measuring the connectedness of financial firms. J Econ 182: 119–134. doi: 10.1016/j.jeconom.2014.04.012
[12]	Diebold FX, Yilmaz K (2015) Financial and macroeconomic connectedness. Oxford University Press.
[13]	Diebold FX, Yilmaz K (2016) Trans-Atlantic equity volatility connectedness: U.S. and European financial institutions, 2004–2014. J Financ Econ 14: 81–127.
[14]	Fengler MR, Gisler KIM (2015) A variance spillover analysis without covariances: What do we miss? J Int Money Finance 51: 174–195. doi: 10.1016/j.jimonfin.2014.11.006
[15]	Friedman G, Italy is the mother of all systemic threats, Sept. 16, 2016. Available from: https://www.forbes.com/sites/johnmauldin/2016/09/13/italy-is-the-mother-of-all-systemic-threats / 2/#5814676e646b.
[16]	Garman MB, Klass MJ (1980) On the estimation of security price volatilities from historical data. J Bus 53: 67–78. doi: 10.1086/296072
[17]	Gätjen R, Schienle G (2004) Measurement of contagion in banks' equity prices. J Int Money Financ 23: 405–459.
[18]	Gropp R, Moerman KIM (2015) Measurement of contagion in banks' equity prices. J Int Money Finance 23: 405–459.
[19]	Guidolin M, Pedio M (2018) Essentials of time series for financial applications. Academic Press.
[20]	Koenker R, Bassett G (1978) Regression quantiles. Econometrica 46: 33–50. doi: 10.2307/1913643
[21]	Koop G, Pesaran MH, Potter SM (1996) £Impulse response analysis in nonlinear multivariate models. J Econ 74: 119–147. doi: 10.1016/0304-4076(95)01753-4
[22]	Lütkepohl H (2005) New introduction to multiple time series analysis. Springer-Verlag Berlin Heidelberg.
[23]	Mackinnon JG (2009) Bootstrap hypothesis testing, In: Belsley DA, Kontoghiorghes EJ, (eds.) Handbook of computational econometrics, John Wiley & Sons, Ltd.
[24]	Pesaran HH, Shin Y (1998) Generalized impulse response analysis in linear multivariate models. Econ Lett 58: 17–29.
[25]	Pounds S, Cheng C (2006) Robust estimation of the false discovery rate. Bioinformatics 22: 1979–1987. doi: 10.1093/bioinformatics/btl328
[26]	The Economist, The Italian job. Italy's teetering banks will be Europe's next crisis, July 9, 2016. Available from: https://www.economist.com/news/leaders/21701756.

Reader Comments

Your name:*

Email:*
© 2018 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)